Every good regulator of a system must be a model of that system.

The central mathematical theorem proved/expounded in the chapter.

Source paper

extracted_from

(1991) · Roger C. Conant · W. Ross Ashby

community

Mechanistic interpretability & model evaluation
members_of
Spans attention head decomposition, benchmark awareness, and genomic pathogenicity prediction via neural models.
Latent capacity, representation, and internal models
members_of
Studies of how neural systems (biological and AI) encode implicit environmental models and adaptive capacities that may be gated or hidden from observable behavior.

concept

system
about
The regulated entity or process; includes air traffic, endocrine balances, money flows.
model
about
A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
good regulator
about
A regulator that achieves effective control; defined implicitly by the theorem as one that is a model of the system.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Model-based regulationconcept0.800
The principle that systems can be controlled through models of their behavior; central to modern control theory and adaptive systems.
In order to actually do anything, the model must act through simulation of something.claim0.780
Key consequence: GPT's power comes from simulating something contingent.
Good Regulator Theoremframework0.778
Theorem stating every good regulator of a system must be a model of that system.
Models are being used ubiquitously for the control of complex dynamic systems.claim0.770
Assertion in the abstract that models are pervasive in controlling complex dynamics, setting the motivation for the theorem.
Good Regulator Theorem (Ashby)concept0.763
Control-theoretic principle: regulator must be isomorphic to system regulated; applied to generative models as control
Base models are good modellers of worlds but not of their own state, because they lack a developed self-model initially.claim0.756
Observation about asymmetry in base model capabilities.
Today, as a step towards the control of complex dynamic systems, models are being used ubiquitously.quote0.748
Opening sentence of the abstract, stating the prevalence of modeling.
Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model.quote0.746
Opening sentence defining self-evidencing.